© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 21288
    Prev
    Next
    INDEX
    Explanations

    adjectives related to strength or power

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate notable achievements or prestigious titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®å®
    -0.66
    omical
    -0.64
     Issue
    -0.61
    atism
    -0.61
    oday
    -0.61
    APH
    -0.59
    ary
    -0.59
    ãĥ¢
    -0.59
    OTE
    -0.58
    Type
    -0.58
    POSITIVE LOGITS
    laim
    0.64
    bled
    0.62
    maxwell
    0.61
    bles
    0.60
    EStream
    0.58
     resilient
    0.57
     (),
    0.57
     fugitive
    0.56
     vigilant
    0.56
     embattled
    0.54
    Activations Density 0.122%

    No Known Activations